com.marklogic.mapreduce

Class MarkLogicOutputFormat<KEYOUT,VALUEOUT>

java.lang.Object

org.apache.hadoop.mapreduce.OutputFormat<KEYOUT,VALUEOUT>

com.marklogic.mapreduce.MarkLogicOutputFormat<KEYOUT,VALUEOUT>

All Implemented Interfaces:

MarkLogicConstants, org.apache.hadoop.conf.Configurable

Direct Known Subclasses:

ContentOutputFormat, KeyValueOutputFormat, NodeOutputFormat, PropertyOutputFormat

public abstract class MarkLogicOutputFormat<KEYOUT,VALUEOUT>
extends org.apache.hadoop.mapreduce.OutputFormat<KEYOUT,VALUEOUT>
implements MarkLogicConstants, org.apache.hadoop.conf.Configurable

MarkLogic-based OutputFormat superclass. Use the provided subclasses, such as PropertyOutputFormat to configure your job.

Field Summary

Fields

Modifier and Type	Field and Description
protected org.apache.hadoop.conf.Configuration	conf
static String	HOSTS_QUERY
static org.apache.commons.logging.Log	LOG

Fields inherited from interface com.marklogic.mapreduce.MarkLogicConstants

ADVANCED_MODE, ASSIGNMENT_POLICY, BASIC_MODE, BATCH_SIZE, BIND_SPLIT_RANGE, COLLECTION_FILTER, CONTENT_TYPE, COPY_COLLECTIONS, COPY_METADATA, COPY_QUALITY, DEFAULT_BATCH_SIZE, DEFAULT_CONTENT_TYPE, DEFAULT_LOCAL_MAX_SPLIT_SIZE, DEFAULT_MAX_SPLIT_SIZE, DEFAULT_OUTPUT_CONTENT_ENCODING, DEFAULT_OUTPUT_XML_REPAIR_LEVEL, DEFAULT_PROPERTY_OPERATION_TYPE, DEFAULT_TXN_SIZE, DIRECTORY_FILTER, DOCUMENT_SELECTOR, EXECUTION_MODE, EXTRACT_URI, INDENTED, INPUT_DATABASE_NAME, INPUT_HOST, INPUT_KEY_CLASS, INPUT_LEXICON_FUNCTION_CLASS, INPUT_MODE, INPUT_PASSWORD, INPUT_PORT, INPUT_QUERY, INPUT_QUERY_LANGUAGE, INPUT_QUERY_TIMESTAMP, INPUT_RESTRICT_HOSTS, INPUT_SSL_OPTIONS_CLASS, INPUT_SSL_PROTOCOL, INPUT_USE_SSL, INPUT_USERNAME, INPUT_VALUE_CLASS, MAX_SPLIT_SIZE, MIN_NODEUPDATE_VERSION, MODE_DISTRIBUTED, MODE_LOCAL, MR_NAMESPACE, NODE_OPERATION_TYPE, OUTPUT_CLEAN_DIR, OUTPUT_COLLECTION, OUTPUT_CONTENT_ENCODING, OUTPUT_CONTENT_LANGUAGE, OUTPUT_CONTENT_NAMESPACE, OUTPUT_DATABASE_NAME, OUTPUT_DIRECTORY, OUTPUT_FAST_LOAD, OUTPUT_FOREST_HOST, OUTPUT_GRAPH, OUTPUT_HOST, OUTPUT_KEY_TYPE, OUTPUT_KEY_VARNAME, OUTPUT_NAMESPACE, OUTPUT_OVERRIDE_GRAPH, OUTPUT_PARTITION, OUTPUT_PASSWORD, OUTPUT_PERMISSION, OUTPUT_PORT, OUTPUT_PROPERTY_ALWAYS_CREATE, OUTPUT_QUALITY, OUTPUT_QUERY, OUTPUT_QUERY_LANGUAGE, OUTPUT_RESTRICT_HOSTS, OUTPUT_SSL_OPTIONS_CLASS, OUTPUT_SSL_PROTOCOL, OUTPUT_STREAMING, OUTPUT_URI_PREFIX, OUTPUT_URI_REPLACE, OUTPUT_URI_SUFFIX, OUTPUT_USE_SSL, OUTPUT_USERNAME, OUTPUT_VALUE_TYPE, OUTPUT_VALUE_VARNAME, OUTPUT_XML_REPAIR_LEVEL, PATH_NAMESPACE, PROPERTY_OPERATION_TYPE, QUERY_FILTER, RECORD_TO_FRAGMENT_RATIO, REDACTION_RULE_COLLECTION, SPLIT_END_VARNAME, SPLIT_QUERY, SPLIT_START_VARNAME, SUBDOCUMENT_EXPRESSION, TEMPORAL_COLLECTION, TXN_SIZE, TYPE_FILTER

Constructor Summary

Constructors

Constructor and Description
MarkLogicOutputFormat()

Method Summary

Modifier and Type	Method and Description
abstract void	checkOutputSpecs(org.apache.hadoop.conf.Configuration conf, com.marklogic.xcc.ContentSource cs)
void	checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext context)
org.apache.hadoop.conf.Configuration	getConf()
protected TextArrayWritable	getHosts(org.apache.hadoop.conf.Configuration conf)
org.apache.hadoop.mapreduce.OutputCommitter	getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context)
protected TextArrayWritable	queryHosts(com.marklogic.xcc.ContentSource cs)
protected TextArrayWritable	queryHosts(com.marklogic.xcc.ContentSource cs, String matchHost, String replaceHost)
void	setConf(org.apache.hadoop.conf.Configuration conf)

Methods inherited from class org.apache.hadoop.mapreduce.OutputFormat

getRecordWriter

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

LOG

public static final org.apache.commons.logging.Log LOG

HOSTS_QUERY

public static final String HOSTS_QUERY

See Also:

Constant Field Values

conf

protected org.apache.hadoop.conf.Configuration conf

Constructor Detail

MarkLogicOutputFormat

public MarkLogicOutputFormat()

Method Detail

checkOutputSpecs

public void checkOutputSpecs(org.apache.hadoop.mapreduce.JobContext context)
                      throws IOException,
                             InterruptedException

Specified by:

checkOutputSpecs in class org.apache.hadoop.mapreduce.OutputFormat<KEYOUT,VALUEOUT>

Throws:

IOException

InterruptedException

getOutputCommitter

public org.apache.hadoop.mapreduce.OutputCommitter getOutputCommitter(org.apache.hadoop.mapreduce.TaskAttemptContext context)
                                                               throws IOException,
                                                                      InterruptedException

Specified by:

getOutputCommitter in class org.apache.hadoop.mapreduce.OutputFormat<KEYOUT,VALUEOUT>

Throws:

IOException

InterruptedException

getConf

public org.apache.hadoop.conf.Configuration getConf()

Specified by:

getConf in interface org.apache.hadoop.conf.Configurable

setConf

public void setConf(org.apache.hadoop.conf.Configuration conf)

Specified by:

setConf in interface org.apache.hadoop.conf.Configurable

getHosts

protected TextArrayWritable getHosts(org.apache.hadoop.conf.Configuration conf)
                              throws IOException

Throws:

IOException

queryHosts

protected TextArrayWritable queryHosts(com.marklogic.xcc.ContentSource cs)
                                throws IOException

Throws:

IOException

queryHosts

protected TextArrayWritable queryHosts(com.marklogic.xcc.ContentSource cs,
                                       String matchHost,
                                       String replaceHost)
                                throws IOException

Throws:

IOException

checkOutputSpecs

public abstract void checkOutputSpecs(org.apache.hadoop.conf.Configuration conf,
                                      com.marklogic.xcc.ContentSource cs)
                               throws IOException

Throws:

IOException